{"id":{"repo_id":"gatech","oai_identifier":"oai:repository.gatech.edu:1853/45889"},"canonical_url":"https://search.dev.ndltd.org/etd/gatech/oai:repository.gatech.edu:1853/45889","repository":{"repo_id":"gatech","name":"Georgia Tech","base_url":"https://repository.gatech.edu/server/oai/request"},"display":{"title":"Improving the quality of speech in noisy environments","abstract":"In this thesis, we are interested in processing noisy speech signals that are meant to be heard by humans, and hence we approach the noise-suppression problem from a perceptual perspective. We develop a noise-suppression paradigm that is based on a model of the human auditory system, where we process signals in a way that is natural to the human ear. Under this paradigm, we transform an audio signal in to a perceptual domain, and processes the signal in this perceptual domain. This approach allows us to reduce the background noise and the audible artifacts that are seen in traditional noise-suppression algorithms, while preserving the quality of the processed speech. We develop a single- and dual-microphone algorithm based on this perceptual paradigm, and conduct subjecting tests to show that this approach outperforms traditional noise-suppression techniques. Moreover, we investigate the cause of audible artifacts that are generated as a result of suppressing the noise in noisy signals, and introduce constraints on the noise-suppression gain such that these artifacts are reduced.","abstract_html":"In this thesis, we are interested in processing noisy speech signals that are meant to be heard by humans, and hence we approach the noise-suppression problem from a perceptual perspective. We develop a noise-suppression paradigm that is based on a model of the human auditory system, where we process signals in a way that is natural to the human ear. Under this paradigm, we transform an audio signal in to a perceptual domain, and processes the signal in this perceptual domain. This approach allows us to reduce the background noise and the audible artifacts that are seen in traditional noise-suppression algorithms, while preserving the quality of the processed speech. We develop a single- and dual-microphone algorithm based on this perceptual paradigm, and conduct subjecting tests to show that this approach outperforms traditional noise-suppression techniques. Moreover, we investigate the cause of audible artifacts that are generated as a result of suppressing the noise in noisy signals, and introduce constraints on the noise-suppression gain such that these artifacts are reduced.","abstract_has_math":false,"creators":["Parikh, Devi"],"institution":"Georgia Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Anderson, David V."],"committee_chairs":[],"committee_members":["Bhatti, Pamela T.","Clements, Mark A.","McClellan, James H.","Vidakovic, Branislav"],"year":2012,"date_issued":"2012-11-06","date_published":"2012-11-06","updated_at":"2026-07-27T19:49:46Z","subjects":["Blind source separation","Perceptual processing","Noise suppression","Speech processing"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1853/45889","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Anderson, David V."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Bhatti, Pamela T.","Clements, Mark A.","McClellan, James H.","Vidakovic, Branislav"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Parikh, Devi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2013-01-17T21:53:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2013-01-17T21:53:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2012-11-06"]},{"key":"dc:publisher","label":"Institution","values":["Georgia Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Blind source separation","Perceptual processing","Noise suppression","Speech processing"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1853/45889"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we are interested in processing noisy speech signals that are meant to be heard by humans, and hence we approach the noise-suppression problem from a perceptual perspective. We develop a noise-suppression paradigm that is based on a model of the human auditory system, where we process signals in a way that is natural to the human ear. Under this paradigm, we transform an audio signal in to a perceptual domain, and processes the signal in this perceptual domain. This approach allows us to reduce the background noise and the audible artifacts that are seen in traditional noise-suppression algorithms, while preserving the quality of the processed speech. We develop a single- and dual-microphone algorithm based on this perceptual paradigm, and conduct subjecting tests to show that this approach outperforms traditional noise-suppression techniques. Moreover, we investigate the cause of audible artifacts that are generated as a result of suppressing the noise in noisy signals, and introduce constraints on the noise-suppression gain such that these artifacts are reduced."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["PhD"]},{"key":"dc:title","label":"Title","values":["Improving the quality of speech in noisy environments"]}]}],"canonical_facts":{"dc:contributor.advisor":["Anderson, David V."],"dc:contributor.committeemember":["Bhatti, Pamela T.","Clements, Mark A.","McClellan, James H.","Vidakovic, Branislav"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Parikh, Devi"],"dc:date.accessioned":["2013-01-17T21:53:42Z"],"dc:date.available":["2013-01-17T21:53:42Z"],"dc:date.issued":["2012-11-06"],"dc:description.abstract":["In this thesis, we are interested in processing noisy speech signals that are meant to be heard by humans, and hence we approach the noise-suppression problem from a perceptual perspective. We develop a noise-suppression paradigm that is based on a model of the human auditory system, where we process signals in a way that is natural to the human ear. Under this paradigm, we transform an audio signal in to a perceptual domain, and processes the signal in this perceptual domain. This approach allows us to reduce the background noise and the audible artifacts that are seen in traditional noise-suppression algorithms, while preserving the quality of the processed speech. We develop a single- and dual-microphone algorithm based on this perceptual paradigm, and conduct subjecting tests to show that this approach outperforms traditional noise-suppression techniques. Moreover, we investigate the cause of audible artifacts that are generated as a result of suppressing the noise in noisy signals, and introduce constraints on the noise-suppression gain such that these artifacts are reduced."],"dc:description.degree":["PhD"],"dc:identifier.uri":["http://hdl.handle.net/1853/45889"],"dc:publisher":["Georgia Institute of Technology"],"dc:subject":["Blind source separation","Perceptual processing","Noise suppression","Speech processing"],"dc:title":["Improving the quality of speech in noisy environments"],"dc:type":["Text"]},"updated_at":"2026-07-27T19:49:46Z"}